Skip to main content
Van Data Team

text model comparison

Gemini 3.8 Flash vs Kimi K3

Gemini 3.8 Flash and Kimi K3 are both current text models, from Google and Moonshot Kimi. Gemini 3.8 Flash is 75% cheaper per 1M input tokens than Kimi K3, $0.75 vs $3. On Arena Text, Gemini 3.8 Flash scores 1497 Elo and Kimi K3 1488 Elo (Arena, measured October 8, 2026). Both accept 1,048,576 tokens of context.

Data verified October 12, 2026 · Dataset 2026-10-12

Share this

Side by side

Standard-tier prices in effect today. The better value in each row is highlighted.

FactGemini 3.8 FlashKimi K3
Price per 1M input tokens$0.75 (better)$3
Price per 1M output tokens$3.75 (better)$15
Cost of 10M input and 2M output tokens$15 (better)$60
Arena Text1497 Elo (#4 of 39) (better)1488 Elo (#7 of 39)
GPQA Diamond95.4% (#3 of 37) (better)93.1% (#15 of 37)
FrontierMath Tiers 1-3 (v2)68.4% (#21 of 37)72.2% (#19 of 37) (better)
SimpleQA Verified69.7% (#7 of 34) (better)50.6% (#18 of 34)
ProviderGoogleMoonshot Kimi
Release dateSeptember 2, 2026July 16, 2026
AccessAPI onlyAPI and open weights
Context window1,048,576 tokens1,048,576 tokens
Max output65,536 tokensNot reported
Inputtext, image, audio, videotext, image
Outputtexttext

Scores:Arena · 2026-10-12Epoch AI · 2026-10-12

Open both in the interactive comparison

When to choose each

Gemini 3.8 Flash

Best for

  • High-volume agentic and coding workloads where per-token cost dominates the decision
  • Multimodal pipelines that need audio, video and PDF input in one model

Watch out for

  • The listed price is promotional and ends 31 December 2026; on 1 January 2027 input and output both double, to $1.50 and $7.50, and cached input goes from $0.075 to $0.15
  • Output pricing is billed inclusive of thinking tokens, so reasoning-heavy prompts cost more than the output length suggests
  • Google’s published comparisons are against its own previous Flash release and were not independently reproduced here
Full Gemini 3.8 Flash profile

Kimi K3

Best for

  • Teams that want a frontier-scale model they can also self-host, with one architecture across both paths
  • Long-context work at mid-tier hosted pricing

Watch out for

  • Hosted rates match Claude Sonnet 5 exactly at $3 / $15 while offering a larger context window, so the comparison turns on capability rather than price
  • Running the open weights shifts cost to infrastructure, which the token rates recorded here do not represent
  • Moonshot’s self-reported results place it ahead of Claude Opus 4.8 and GPT-5.5 but behind Claude Fable 5 and GPT-5.6 Sol; none of this was reproduced independently here
Full Kimi K3 profile

Gemini 3.8 Flash vs Kimi K3 FAQ

Which is cheaper, Gemini 3.8 Flash or Kimi K3?

Gemini 3.8 Flash is 75% cheaper per 1M input tokens than Kimi K3, $0.75 vs $3. For 10M input and 2M output tokens, Gemini 3.8 Flash costs $15 and Kimi K3 $60 at standard rates.

Which scores higher on independent benchmarks, Gemini 3.8 Flash or Kimi K3?

Gemini 3.8 Flash leads on Arena Text, 1497 Elo to 1488 Elo; Gemini 3.8 Flash leads on GPQA Diamond, 95.4% to 93.1%; Kimi K3 leads on FrontierMath Tiers 1-3 (v2), 72.2% to 68.4%. Scores are independent evaluations, not either vendor's launch figures.

Which has the larger context window, Gemini 3.8 Flash or Kimi K3?

Both accept 1,048,576 tokens of context.

Can I run Gemini 3.8 Flash or Kimi K3 myself?

Kimi K3 is released as open weights you can run yourself; Gemini 3.8 Flash is available through its provider's API only.

Related comparisons

Production evaluation

Choosing between Gemini 3.8 Flash and Kimi K3?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • A head-to-head evaluation on your real workload
  • Routing between models by cost and difficulty
Compare all modelsDiscuss your evaluation